© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 1090
    Prev
    Next
    INDEX
    Explanations

    phrases that prompt actions, particularly those starting with "take" or "give."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ыгана
    -0.45
    PhysRev
    -0.45
     disponibilités
    -0.45
    shadowOffset
    -0.43
     snippetHide
    -0.42
    ioon
    -0.41
    endphp
    -0.41
    //
    -0.41
    mitsubishi
    -0.40
    bbc
    -0.39
    POSITIVE LOGITS
    tagHelperRunner
    0.93
     look
    0.86
    look
    0.77
     الرياضيه
    0.73
     LOOK
    0.68
    EndGlobalSection
    0.68
    MemoryWarning
    0.64
     glance
    0.61
     whirl
    0.60
    Carriera
    0.60
    Activations Density 0.090%

    No Known Activations